© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82535
    Prev
    Next
    INDEX
    Explanations

    headings and section starts

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on digital time‐code or timestamp patterns (numeric sequences separated by colons).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рного
    -0.90
     tarihi
    -0.82
    Url
    -0.82
    gründet
    -0.79
    jna
    -0.79
    ೨
    -0.78
    rawler
    -0.78
    🔟
    -0.78
     podcasts
    -0.78
     Motta
    -0.77
    POSITIVE LOGITS
    ავ
    0.83
    forcing
    0.82
    ‖
    0.82
    ignor
    0.82
    眼中
    0.80
     (€
    0.80
     добрый
    0.79
     fundamentales
    0.78
     inherit
    0.78
     stills
    0.77
    Activations Density 0.004%

    No Known Activations